# GPT-5.2 Codex vs Qwen3 32B

> GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 39.2 on the Noometry Index. Qwen3 32B costs 3.9× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-2-codex-vs-qwen3-32b
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in agentic & tool use, where GPT-5.2 Codex leads 41.0 to 32.6.
- Qwen3 32B is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
- GPT-5.2 Codex accepts more context: 400K tokens versus 131K.
- Qwen3 32B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.2 Codex | Qwen3 32B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.6 | 39.2 |
| Rank | 111 | 172 |
| Context | 400K | 131K |
| Input $/M | $1.75 | $0.70 |
| Output $/M | $14 | $2.80 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.2 Codex: 45.5 (#71)
- Qwen3 32B: 37.7 (#190)

| Benchmark | GPT-5.2 Codex | Qwen3 32B |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| Aider Polyglot | — | 40% |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| SciCode | — | 35.4% |
| LMArena Coding | — | 1358 |
| ALE-Bench | 1,300 | — |

## Agentic & Tool Use

- GPT-5.2 Codex: 41.0 (#22)
- Qwen3 32B: 32.6 (#62)

| Benchmark | GPT-5.2 Codex | Qwen3 32B |
|---|---|---|
| Terminal-Bench | 66.5% | — |
| Berkeley Function Calling Leaderboard | — | 48.7% |

## Reasoning

- GPT-5.2 Codex: —
- Qwen3 32B: 20.2 (#241)

| Benchmark | GPT-5.2 Codex | Qwen3 32B |
|---|---|---|
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | — | 1334 |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |

## Math

- GPT-5.2 Codex: —
- Qwen3 32B: 39.7 (#99)

| Benchmark | GPT-5.2 Codex | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| LMArena Math | — | 1399 |

## Knowledge

- GPT-5.2 Codex: —
- Qwen3 32B: 40.0 (#125)

| Benchmark | GPT-5.2 Codex | Qwen3 32B |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| LMArena Expert | — | 1362 |

## Multilingual

- GPT-5.2 Codex: —
- Qwen3 32B: 45.6 (#167)

| Benchmark | GPT-5.2 Codex | Qwen3 32B |
|---|---|---|
| LMArena Non-English | — | 1317 |
| LMArena Chinese | — | 1357 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1311 |

## Instruction Following

- GPT-5.2 Codex: —
- Qwen3 32B: 68.9 (#179)

| Benchmark | GPT-5.2 Codex | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | — | 1305 |

## Long Context

- GPT-5.2 Codex: —
- Qwen3 32B: 43.8 (#87)

| Benchmark | GPT-5.2 Codex | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | — | 74.2% |
| LMArena Longer Query | — | 1327 |

## Writing & Preference

- GPT-5.2 Codex: —
- Qwen3 32B: 52.9 (#163)

| Benchmark | GPT-5.2 Codex | Qwen3 32B |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1297 |
| LMArena Multi-Turn | — | 1331 |

## FAQ

### Is GPT-5.2 Codex better than Qwen3 32B?

GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 39.2 on the Noometry Index. Qwen3 32B costs 3.9× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.2 Codex or Qwen3 32B?

Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.

### Is GPT-5.2 Codex or Qwen3 32B better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.5 versus 37.7 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.2 Codex does, with 400K tokens against 131K.

### How many benchmarks do GPT-5.2 Codex and Qwen3 32B share?

0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Qwen3 32B has 26.